vLLM is an inference and serving engine for large language models. From 0.19.0 until 0.32.0, authenticated callers can supply a request chat template when no server-side --chat-template is configured, or a malicious model repository can provide a template that is compiled and rendered by tokenizer.apply_chat_template() without a wall-clock timeout, output-size limit, or iteration bound. Rendering runs in a ThreadPoolExecutor with one worker by default, so a nonterminating render can block /v1/responses and other chat-template users after the request ends, while an output-expanding render can exhaust server memory. Harmony models are not affected because they do not use this Jinja path. This issue is fixed in version 0.32.0.
{
"cna_assigner": "GitHub_M",
"cwe_ids": [
"CWE-400",
"CWE-770",
"CWE-834"
],
"osv_generated_from": "https://github.com/CVEProject/cvelistV5/tree/main/cves/2026/115xxx/CVE-2026-115911.json"
}{
"extracted_events": [
{
"cpe": "cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*",
"range": [
{
"introduced": "0.19.0"
},
{
"fixed": "0.32.0"
}
],
"source": "CPE_RANGE"
},
{
"range": [
{
"fixed": "cff08b461e086523cee8bba5bd3c66d302625134"
}
],
"source": "REFERENCES_COMMIT"
},
{
"original_tag": "v0.32.0",
"range": [
{
"fixed": "5df63a7203cdb9328d824a27b682e77c7b9928be"
}
],
"source": "REFERENCES_TAG"
}
]
}